Noa Braverman

1
Forecasting epilepsy from theheart rate signal

• Noa Braverman

2
Introduction

• potential seizure detector
• EEG as brain-state mirror
• instantaneous heart rate
• ictal (sinus)tachycardia

3
Introduction cont.

• the brain-heart axis
• Vagus Nerve
• The existence of
• pre- ictal phase

4
Introduction cont.

• This study
• Forecasting seizures
• Partial complex humans
• Generalized - rats
• Novel method for HRV analysis
• Ph.D. D.H.Kerem
• Ph.D. A.B.Geva

5
Known Methods

• Spectral analysis of the time series of R-R
  intervals
• non-linear dynamics
• shortcoming -
• inability to account for non-stationary states
  and transients

6
Known Methods cont.

• time-varying power spectral density estimation
• Attractors and correlation dimensions
• Karhunen-Love transform-based signal analysis
  method

7
Fuzzy clustering approach

• comet or torpedo-shaped
• unsupervised method advantage

8
Chosen method

• EEG-contained information of HRV.
• (GEVA and KEREM, 1998)
• an unsupervised method designed to deal with
  merging and overlapping states
• ability to spot and classify

9
Data resources

• Humans

• Rats

• Humans
• 21 patients records, archived records
• The recording machinery
• simultaneous EEG and video recording
• ECG channel
• visual inspection by an EEG expert
• The actual database

• Rats
• Hyperbaric-oxygen
• ECG and EEG filtering and recording
• Rats effects
• Time period analyzing
• Control rats Vs. research rats

• OUTPUT

10
Method cont.

• Choice of analysis parameters
• ?RRI Vs. RRI
• embedding dimension N
• For this experiment
• Both features
• N 3
• number of clusters

11
Method cont.

• Forecasting criteria
• Appearance
• Disappearance
• Dominant
• False negative - False positive

12
Results

• Humans

• Rats

• Successful forecasting
• Tachycardia period
• success rate
• 86
• ?RRI Vs. RRI
• forecasting times
• 1.5-11 min.

• Successful forecasting
• Bradycardia period
• success rate
• 82
• ?RRI Vs. RRI
• forecasting times
• 2.5-9 min.

13
Results cont.

• Humans

• Rats

• prediction failures
• false negative
• One case
• false positive
• Two cases
• Longer records

• prediction failures
• false negative
• none
• false positive
• Two cases
• Ignoring changes shown in control rats

14
Discussion

• information in the pre-ictal ECG signal
• HRV Time-Frequency analysis by NOVAK
• pre-ictal state
• time-frequency forecasters
• Records length

15
Discussion cont.

• the sleeping state
• Alerting systems
• generalized seizures forecasting

16
Individual opinion

• Next step
• Testing State-rely data
• Non-arbitrary patient selection
• Age specific

17
Any Questions?